Facial Expression Recognition Based on the Multi-species Genetic Algorithm
DU Jia-you · Journal of Hangzhou Dianzi University · 2013
In this paper,a novel method of expression recognition is presented.Firstly,principal component analysis(PCA) is used to extract face expression features;Secondly,multi-species genetic algorithm(GA) is used to select excellent support vector machine(SVM) kernel function;Lastly,this support vector machine classifier based on genetic algorithm is used to recognize seven kinds of face expression.Experiments are performed on the Japanese female facial expression(JAFFE) database.And compared to other classifiers,the support vector machine classifier based on genetic algorithm can get better recognition ratio.